人工智能与机器学习在头晕和眩晕中的眼动应用：综合综述。
Artificial Intelligence and Machine Learning for Eye Movements in Dizziness and Vertigo: A Comprehensive Review.
文献信息
| PMID | 42869523 |
|---|---|
| 原文 | 在 PubMed 查看原文 ↗ |
| 发表日期 | 2026 |
| 作者 | David P W Rastall |
| 作者单位 | Department of Neurology, Armstrong Institute Center for Diagnostic Excellence, Johns Hopkins University School of Medicine, 750 East Pratt Street, 16th Floor, Baltimore, MD 21202, USA. Electronic address: drastal1@jhmi.edu. |
| 期刊 | Neurologic clinics |
| SCI 分区 | Q2 |
| IF | 3.3 |
| 研究类型 | 综述 Meta · 临床 |
| 所属专科 | 耳科 |
中文摘要
头晕和眩晕是常见的神经系统主诉，在急诊和门诊环境中均难以准确诊断。尽管复杂，这些疾病常表现为特定的眼动异常，其中包含可用于定位和诊断的精确信号。人工智能（AI）和机器学习的最新进展使得对通过视频眼震图及相关技术获得的眼动记录进行自动分析成为可能，从而降低了其临床应用的障碍。在本综述中，分析了基于AI的眼动方法用于诊断头晕和眩晕，并按若干临床诊断任务进行组织，包括良性阵发性位置性眩晕、急性前庭综合征和卒中分诊。
英文摘要
Dizziness and vertigo, common neurologic complaints, remain challenging to diagnose accurately in both emergency and outpatient settings. Although complex, these conditions frequently present with specific abnormalities of eye movement that contain precise signals allowing for localization and diagnosis. Recent advances in artificial intelligence (AI) and machine learning have enabled automated analysis of eye-movement recordings obtained using video-oculography and related technologies, reducing barriers to their clinical use. In this review, AI-based approaches to eye movement are analyzed to diagnose dizziness and vertigo, organized using several clinical diagnostic tasks, including benign paroxysmal positional vertigo, acute vestibular syndrome and stroke triage.